Systems and Methods Relating to Bot Authoring by Mining Intents from Natural Language Conversations

7. The method of claim 6, wherein the selecting the salient intents from the candidate intents comprises selecting ones of the candidate intents that are determined to appear more frequently in the intent-bearing utterances than other ones of the candidate intents.

8. The method of claim 6, wherein the one or more criteria by which the salient intents are selected from the candidate intents comprises a criterion based on Latent Semantic Analysis.

13. The method of claim 12, wherein the associating the utterances from the conversation data with the salient intent groups comprises associating the intent alternative producing the highest computed degree of semantic similarity only if the highest computed degree of semantic similarity is also found to exceed a predetermined similarity threshold.

20. The system of claim 19, wherein the selecting the salient intents from the candidate intents comprises selecting ones of the candidate intents that are determined to appear more frequently in the intent-bearing utterances than other ones of the candidate intents.

21. The system of claim 19, wherein the one or more criteria by which the salient intents are selected from the candidate intents comprises a criterion based on Latent Semantic Analysis.

26. The system of claim 25, wherein the associating the utterances from the conversation data with the salient intent groups comprises associating the intent alternative producing the highest computed degree of semantic similarity only if the highest computed degree of semantic similarity is also found to exceed a predetermined similarity threshold.